Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms
Hyperspectral technology has enabled rapid and efficient nitrogen monitoring in crops. However, most approaches involve direct monitoring of nitrogen content or physiological and biochemical indicators directly related to nitrogen, which cannot reflect the overall plant nutritional status. Two impor...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/12/3/455 |
| _version_ | 1797623514279182336 |
|---|---|
| author | Peng Han Yaping Zhai Wenhong Liu Hairong Lin Qiushuang An Qi Zhang Shugen Ding Dawei Zhang Zhenyuan Pan Xinhui Nie |
| author_facet | Peng Han Yaping Zhai Wenhong Liu Hairong Lin Qiushuang An Qi Zhang Shugen Ding Dawei Zhang Zhenyuan Pan Xinhui Nie |
| author_sort | Peng Han |
| collection | DOAJ |
| description | Hyperspectral technology has enabled rapid and efficient nitrogen monitoring in crops. However, most approaches involve direct monitoring of nitrogen content or physiological and biochemical indicators directly related to nitrogen, which cannot reflect the overall plant nutritional status. Two important photosynthetic traits, the fraction of absorbed photosynthetically active radiation (FAPAR) and the net photosynthetic rate (Pn), were previously shown to respond positively to nitrogen changes. Here, Pn and FAPAR were used for correlation analysis with hyperspectral data to establish a relationship between nitrogen status and hyperspectral characteristics through photosynthetic traits. Using principal component and band autocorrelation analyses of the original spectral reflectance, two band positions (350–450 and 600–750 nm) sensitive to nitrogen changes were obtained. The performances of four machine learning algorithm models based on six forms of hyperspectral transformations showed that the light gradient boosting machine (LightGBM) model based on the hyperspectral first derivative could better invert the Pn of function–leaves in cotton, and the random forest (RF) model based on hyperspectral first derivative could better invert the FAPAR of the cotton canopy. These results provide advanced metrics for non–destructive tracking of cotton nitrogen status, which can be used to diagnose nitrogen nutrition and cotton growth status in large farms. |
| first_indexed | 2024-03-11T09:30:02Z |
| format | Article |
| id | doaj.art-09cd84aaa6f741189b62a79a1a3343ba |
| institution | Directory Open Access Journal |
| issn | 2223-7747 |
| language | English |
| last_indexed | 2024-03-11T09:30:02Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj.art-09cd84aaa6f741189b62a79a1a3343ba2023-11-16T17:42:37ZengMDPI AGPlants2223-77472023-01-0112345510.3390/plants12030455Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning AlgorithmsPeng Han0Yaping Zhai1Wenhong Liu2Hairong Lin3Qiushuang An4Qi Zhang5Shugen Ding6Dawei Zhang7Zhenyuan Pan8Xinhui Nie9Key Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaResearch Institute of Economic Crops, Xinjiang Academy of Agricultural Sciences, Urumqi 830091, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaKey Laboratory of Oasis Ecology Agricultural of Xinjiang Production and Construction Corps, Agricultural College, Shihezi University, Shihezi 832003, ChinaHyperspectral technology has enabled rapid and efficient nitrogen monitoring in crops. However, most approaches involve direct monitoring of nitrogen content or physiological and biochemical indicators directly related to nitrogen, which cannot reflect the overall plant nutritional status. Two important photosynthetic traits, the fraction of absorbed photosynthetically active radiation (FAPAR) and the net photosynthetic rate (Pn), were previously shown to respond positively to nitrogen changes. Here, Pn and FAPAR were used for correlation analysis with hyperspectral data to establish a relationship between nitrogen status and hyperspectral characteristics through photosynthetic traits. Using principal component and band autocorrelation analyses of the original spectral reflectance, two band positions (350–450 and 600–750 nm) sensitive to nitrogen changes were obtained. The performances of four machine learning algorithm models based on six forms of hyperspectral transformations showed that the light gradient boosting machine (LightGBM) model based on the hyperspectral first derivative could better invert the Pn of function–leaves in cotton, and the random forest (RF) model based on hyperspectral first derivative could better invert the FAPAR of the cotton canopy. These results provide advanced metrics for non–destructive tracking of cotton nitrogen status, which can be used to diagnose nitrogen nutrition and cotton growth status in large farms.https://www.mdpi.com/2223-7747/12/3/455cottonnitrogen monitoringabsorbed photosynthetically active radiationnet photosynthetic rateremote sensing monitoringmachine learning algorithms models |
| spellingShingle | Peng Han Yaping Zhai Wenhong Liu Hairong Lin Qiushuang An Qi Zhang Shugen Ding Dawei Zhang Zhenyuan Pan Xinhui Nie Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms Plants cotton nitrogen monitoring absorbed photosynthetically active radiation net photosynthetic rate remote sensing monitoring machine learning algorithms models |
| title | Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms |
| title_full | Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms |
| title_fullStr | Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms |
| title_full_unstemmed | Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms |
| title_short | Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (<i>Gossypium hirsutum</i> L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms |
| title_sort | dissection of hyperspectral reflectance to estimate photosynthetic characteristics in upland cotton i gossypium hirsutum i l under different nitrogen fertilizer application based on machine learning algorithms |
| topic | cotton nitrogen monitoring absorbed photosynthetically active radiation net photosynthetic rate remote sensing monitoring machine learning algorithms models |
| url | https://www.mdpi.com/2223-7747/12/3/455 |
| work_keys_str_mv | AT penghan dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT yapingzhai dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT wenhongliu dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT haironglin dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT qiushuangan dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT qizhang dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT shugending dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT daweizhang dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT zhenyuanpan dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms AT xinhuinie dissectionofhyperspectralreflectancetoestimatephotosyntheticcharacteristicsinuplandcottonigossypiumhirsutumilunderdifferentnitrogenfertilizerapplicationbasedonmachinelearningalgorithms |